1) La descarga del recurso depende de la página de origen
2) Para poder descargar el recurso, es necesario ser usuario registrado en Universia

Opción 1: Descargar recurso

Detalles del recurso


Current web servers are highly multithreaded applications whose scalability benefits from the current multicore/multiprocessor trend. However, some workloads can not capitalize on this because their performance is limited by the available memory and/or the disk bandwidth, which prevents the server from taking advantage of the computing resources provided by the system. To solve this situation we propose the use of main memory compression techniques to increment the available memory and mitigate the disk band- width problem, allowing the web server to improve its use of CPU system resources. In this paper we implement to the Linux OS a full SMP capable main memory compression subsystem to increase the performance of a web server running the SPECweb2005 benchmark. Although main memory compression is not a new technique per-se, its use in a multicore environment running heavily multithreaded applications like a web server introduces new challenges in the technique, such as scalability issues and the trade-off between the compressed memory size and the computational power required to achieve it. Finally, the evaluation of our implementaiton shows promising results such as a 30% web server throughput improvement and a 70% reduction in the disk bandwidth usage.

Pertenece a

UPCommons - E-prints UPC Universitat Politècnica de Catalunya   


Beltran Querol, Vicenç -  Torres Viñals, Jordi -  Ayguadé Parra, Eduard - 

Id.: 55143086

Idioma: inglés  - 

Versión: 1.0

Estado: Final

Tipo:  8 p. - 

Palabras claveÀrees temàtiques de la UPC -  Informàtica -  Arquitectura de computadors - 

Tipo de recurso: Conference lecture  - 

Tipo de Interactividad: Expositivo

Nivel de Interactividad: muy bajo

Audiencia: Estudiante  -  Profesor  -  Autor  - 

Estructura: Atomic

Coste: no

Copyright: sí

: Open Access

Formatos:  8 p. - 

Requerimientos técnicos:  Browser: Any - 

Relación: [References] http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=04724333

Fecha de contribución: 05-may-2013


* Beltran, V.; Torres, J.; Ayguadé, E. Improving web server performance through main memory compression. A: IEEE International Conference on Parallel and Distributed Systems. "Fourteenth IEEE International Conference on Parallel and Distributed Systems". Melbourne: IEEE Computer Society, 2008, p. 303-310.
* 978-0-7695-3434-3
* 10.1109/ICPADS.2008.15

Otros recursos del mismo autor(es)

  1. Quantitative evaluation of register pressure on software pipeline loops Software Pipelining is a loop scheduling technique that extracts loop parallelism by overlapping the...
  2. DDT: a research tool for automatic data distribution in HPF This article describes the main features and implementation of our automatic data distribution resea...
  3. Exploiting memory affinity in OpenMP through schedule reuse In this paper we explore the possibility of reusing schedules to improve the scalability of numerica...
  4. New OpenMP directives for irregular data access loops Many scientific applications involve array operations that are sparse in nature, ie array elements d...
  5. Dual-level parallelism exploitation with OpenMP in coastal ocean circulation modeling Two alternative dual-level parallel implementations of the Multiblock Grid Princeton Ocean Model (MG...

Otros recursos de la misma colección

  1. A local constitutive model for the discrete element method: application to geomaterials and concrete This paper presents a local constitutive model for modelling the linear and non linear behavior of s...
  2. Increasing yield of nanocrystalline cellulose preparation process by a cellulase pretreatment In this work the introduction of a cellulase treatment prior to NCC isolation was assessed. NCC was ...
  3. FUTUR. Portal for the scientific output of researchers at the Universitat Politècnica de Catalunya Postprint (author’s final draft)
  4. Les llàgrimes de Santa Eulàlia Award-winning
  5. A meshless finite point method for three dimensional analysis of compressible flow problems involving moving boundaries and adaptivity A finite point method for solving compressible flow problems involving moving boundaries and adaptiv...

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.